Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3047 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.1721. Min Range: -5.1721

Max Act: 5.1721. Min Act: -0.0000

Data Index: 1232644 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 5.1721. Min Range: -5.1721

Max Act: 4.2757. Min Act: -0.0000

Data Index: 213167 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 5.1721. Min Range: -5.1721

Max Act: 4.2993. Min Act: -0.0000

Data Index: 450919 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.7185. Min Act: -0.0000

Data Index: 132236 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.8933. Min Act: -0.0000

Data Index: 1310348 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 5.1721. Min Range: -5.1721

Max Act: 4.0547. Min Act: -0.0000

Data Index: 344206 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.9739. Min Act: -0.0000

Data Index: 482378 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.8463. Min Act: -0.0000

Data Index: 497810 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.9396. Min Act: -0.0000

Data Index: 1236354 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.7413. Min Act: -0.0000

Data Index: 287922 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.8513. Min Act: -0.0000

Data Index: 632780 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.6890. Min Act: -0.0000

Data Index: 428169 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.8061. Min Act: -0.0000

Data Index: 281918 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.7498. Min Act: -0.0000

Data Index: 759544 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.6965. Min Act: -0.0000

Data Index: 1201703 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.6859. Min Act: -0.0000

Data Index: 781856 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.4786. Min Act: -0.0000

Data Index: 432681 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.7604. Min Act: -0.0000

Data Index: 917661 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.7522. Min Act: -0.0000

Data Index: 615878 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 5.1721. Min Range: -5.1721

Max Act: 3.6391. Min Act: -0.0000

Data Index: 882217 (C4 (Web Text))

Max Activating Token Index: 898